Table 3 Average recall for different data sets.
From: Application of kernel functions for accurate similarity search in large chemical databases
Dataset | G-hash | WA | C-tree | Fingerprint | gIndex |
|---|---|---|---|---|---|
PDE5 | 73.19 | 58.06 | 46.93 | 58.80 | 73.60* |
CDK2 | 67.17 | 55.87 | 46.70 | 47.20 | 67.82* |
COX2 | 64.22 | 63.57 | 51.46 | 54.21 | 87.01* |
FXa | 64.63 | 58.23 | 42.06 | 55.62 | 71.19* |
AIA | 80.70* | 64.81 | 55.33 | 54.41 | 60.20 |
AChE | 76.13 | 63.63 | 44.15 | 27.40 | 85.20* |
ALF | 69.84 | 61.25 | 53.83 | 75.98* | 65.00 |
EGF-R | 86.22* | 79.64 | 55.81 | 54.00 | 81.61 |
HIV-P | 80.44* | 63.4 | 47.62 | 42.20 | 75.40 |
HSP90 | 76.31 | 63.4 | 47.62 | 71.00 | 91.38* |
MAPK | 86.83* | 70.52 | 72.16 | 42.01 | 85.79 |
HIV-RT | 72.83 | 67.78 | 56.78 | 60.80 | 73.40* |